Occluded Vehicle Detection via Multi-Scale Hybrid Attention Mechanism in the Road Scene
The obstruction of vehicles by surrounding vehicles, obstacles, etc. is a common phenomenon in the practical application of automatic driving. In view of the problem that the vehicle’s vision is affected by the occlusion, the vehicle feature information is incomplete, resulting in the low detection...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-08-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/11/17/2709 |
| _version_ | 1797495836721020928 |
|---|---|
| author | Tianmin Deng Xuhui Liu Li Wang |
| author_facet | Tianmin Deng Xuhui Liu Li Wang |
| author_sort | Tianmin Deng |
| collection | DOAJ |
| description | The obstruction of vehicles by surrounding vehicles, obstacles, etc. is a common phenomenon in the practical application of automatic driving. In view of the problem that the vehicle’s vision is affected by the occlusion, the vehicle feature information is incomplete, resulting in the low detection accuracy of the occlusion vehicle, and the occlusion vehicle detection method based on the multi-scale hybrid attention mechanism is proposed. The paper aims to fully excavate the advantages of multi-scale feature extraction, channel/space attention and other modules, and to design a multi-scale hybrid attention module suitable for occlusion vehicle detection to improve the detection accuracy of occlusion vehicles. Multi-scale features are enriched by the grouping convolution of different sizes of multi-scale feature extraction networks, and the parallel connection channels and spatial attention modules form different scale hybrid domain attention modules, which enhance the local feature information of the occluded vehicles and realize the reinforcement learning of multi-scale features and the suppression of occlusion interference information. Experimental results show that in the self-made occlusion vehicle dataset and the BDD100K occlusion vehicle dataset, the average mean accuracy of this method is 95.2% and 59.3%, respectively, which is 1.5% and 2.9% higher than that of the baseline network YOLOv5, respectively. |
| first_indexed | 2024-03-10T01:55:17Z |
| format | Article |
| id | doaj.art-b762fb368102446cba0c8cabd585b4ce |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-10T01:55:17Z |
| publishDate | 2022-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-b762fb368102446cba0c8cabd585b4ce2023-11-23T12:58:05ZengMDPI AGElectronics2079-92922022-08-011117270910.3390/electronics11172709Occluded Vehicle Detection via Multi-Scale Hybrid Attention Mechanism in the Road SceneTianmin Deng0Xuhui Liu1Li Wang2School of Traffic and Transportation, Chongqing Jiaotong University, Chongqing 400074, ChinaSchool of Traffic and Transportation, Chongqing Jiaotong University, Chongqing 400074, ChinaSchool of Traffic and Transportation, Chongqing Jiaotong University, Chongqing 400074, ChinaThe obstruction of vehicles by surrounding vehicles, obstacles, etc. is a common phenomenon in the practical application of automatic driving. In view of the problem that the vehicle’s vision is affected by the occlusion, the vehicle feature information is incomplete, resulting in the low detection accuracy of the occlusion vehicle, and the occlusion vehicle detection method based on the multi-scale hybrid attention mechanism is proposed. The paper aims to fully excavate the advantages of multi-scale feature extraction, channel/space attention and other modules, and to design a multi-scale hybrid attention module suitable for occlusion vehicle detection to improve the detection accuracy of occlusion vehicles. Multi-scale features are enriched by the grouping convolution of different sizes of multi-scale feature extraction networks, and the parallel connection channels and spatial attention modules form different scale hybrid domain attention modules, which enhance the local feature information of the occluded vehicles and realize the reinforcement learning of multi-scale features and the suppression of occlusion interference information. Experimental results show that in the self-made occlusion vehicle dataset and the BDD100K occlusion vehicle dataset, the average mean accuracy of this method is 95.2% and 59.3%, respectively, which is 1.5% and 2.9% higher than that of the baseline network YOLOv5, respectively.https://www.mdpi.com/2079-9292/11/17/2709occluded vehicle detectionmulti-scale feature extractionchannel attention mechanismspatial attention mechanismhybrid domain attention module |
| spellingShingle | Tianmin Deng Xuhui Liu Li Wang Occluded Vehicle Detection via Multi-Scale Hybrid Attention Mechanism in the Road Scene Electronics occluded vehicle detection multi-scale feature extraction channel attention mechanism spatial attention mechanism hybrid domain attention module |
| title | Occluded Vehicle Detection via Multi-Scale Hybrid Attention Mechanism in the Road Scene |
| title_full | Occluded Vehicle Detection via Multi-Scale Hybrid Attention Mechanism in the Road Scene |
| title_fullStr | Occluded Vehicle Detection via Multi-Scale Hybrid Attention Mechanism in the Road Scene |
| title_full_unstemmed | Occluded Vehicle Detection via Multi-Scale Hybrid Attention Mechanism in the Road Scene |
| title_short | Occluded Vehicle Detection via Multi-Scale Hybrid Attention Mechanism in the Road Scene |
| title_sort | occluded vehicle detection via multi scale hybrid attention mechanism in the road scene |
| topic | occluded vehicle detection multi-scale feature extraction channel attention mechanism spatial attention mechanism hybrid domain attention module |
| url | https://www.mdpi.com/2079-9292/11/17/2709 |
| work_keys_str_mv | AT tianmindeng occludedvehicledetectionviamultiscalehybridattentionmechanismintheroadscene AT xuhuiliu occludedvehicledetectionviamultiscalehybridattentionmechanismintheroadscene AT liwang occludedvehicledetectionviamultiscalehybridattentionmechanismintheroadscene |